Shinei Kudo, director of the Gastroenterological Center, Showa University Northern Yokohama Hospital, has developed a colonoscopy support system using artificial intelligence (AI) in collaboration with Professor Kensaku Mori of the Graduate School of Informatics, Nagoya University.
Colorectal cancer has been on the rise in recent years, ranking first in the number of cancer deaths among women and third among men, and effective measures are required.Colonoscopy is said to be useful not only for the detection and treatment of colorectal cancer but also for the prevention, but on the other hand, about 1% of small neoplastic lesions are overlooked in one examination. There is also a report that.With the aim of reducing such oversights, the joint group has been developing artificial intelligence that comprehensively supports endoscopic medical care.
As a result, we have succeeded in developing an AI that detects polyps and cancer in real time and assists doctors in finding lesions. It is said that 94% of lesions could be detected by artificial intelligence.Another feature is that it is evaluated in a strict environment close to actual clinical practice by verifying with moving images instead of still images.This achievement was published in the June 2018 issue of the highly prestigious journal of the American Society of Gastroenterology, "Gastroenterology."This is the first time in the world that a doctor has reported an automatic detection paper using AI for colonoscopy.
This AI has been implemented as software that can be operated in real time by the Graduate School of Informatics, Nagoya University and Cybernet Systems Co., Ltd., and clinical research has already begun.This result is expected to reduce the risk of overlooking microcancer and precancerous lesions and suppress death from colorectal cancer.
Paper information:[Gastroenterology] Artificial Intelligence-Assisted Polyp Detection for Colonoscopy: Initial Experience
